Security audit
GM3 Alertworthy Feed
Security checks across malware telemetry and agentic risk
Overview
This skill is a narrow read-only market-data API reference, with the main consideration being safe handling of the required GM3 API key.
Install only if you are comfortable letting an agent use your GM3 Developer API key to call the documented read-only feed. Store the key as a secret, avoid logging Authorization headers, and treat returned market data as analysis input rather than trading instructions.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.